| MATHEMATICS (TURKISH, PHD) | |||||
| PhD | TR-NQF-HE: Level 8 | QF-EHEA: Third Cycle | EQF-LLL: Level 8 | ||
| Course Code | Course Name | Semester | Theoretical | Practical | Credit | ECTS |
| SEN4107 | Introduction to Neural Networks | Fall | 3 | 0 | 3 | 6 |
| The course opens with the approval of the Department at the beginning of each semester |
| Language of instruction: | En |
| Type of course: | Departmental Elective |
| Course Level: | |
| Mode of Delivery: | Hybrid |
| Course Coordinator : | Dr. Öğr. Üyesi AYLA GÜLCÜ |
| Course Objectives: | Understanding the mathematical foundations of deep learning, learning basic neural network structures like feed-forward, convolutional and recurrent neural networks; examining the application areas of different networks and using these structures for solving real life problems. Recognition of reinforcement learning techniques. |
|
The students who have succeeded in this course; Understands the mathematics of deep neural networks Demonstrates the ability to design, build and train deep feed-forward neural networks using PyTorch Demonstrates the ability to design, build and train convolutional neural networks using PyTorch Learns object recognition and detection models Demonstrates the ability to design, build and train recurrent neural networks using PyTorch Demonstrates the ability to build, train and fine tune neural network models for the real world problems Learns reinforcement learning techniques |
| Deep feed-forward neural networks, Pytorch deep learning framework, convolutional neural networks, object recognition and object detection problems, recurrent neural networks, attention mechanism, deep generative models and reinforcement learning. |
| Week | Subject | Related Preparation | |
| 1) | Introduction to Deep Learning | ||
| 2) | Overview of machine learning, linear classifiers, loss functions | ||
| 3) | Stochastic gradient descent and contemporary variants, back-propagation | ||
| 4) | Feed-forward networks and training | ||
| 5) | Feed-forward networks and training (PyTorch and cloud) | ||
| 6) | Convolutional neural networks (CNNs) | ||
| 7) | Understanding and Visualizing CNNs | ||
| 8) | Midterm Exam | ||
| 9) | Object Detection Approaches | ||
| 10) | Recurrent neural networks | ||
| 11) | Recurrent neural networks | ||
| 12) | Attention and Memory | ||
| 13) | Deep generative models | ||
| 14) | Deep reinforcement learning | ||
| 15) | |||
| Course Notes: | “Deep Learning by Ian Goodfellow”, Yoshua Bengio and Aaron Courville, MIT Press (2016) |
| References: | “Hands-On Neural Networks with PyTorch 1.0”, Vihar Kurama, Pakt Publishing (2019) https://www.deeplearningbook.org/ “Machine Learning: A Probabilistic Perspective”, K. P. Murphy, MIT Press (2012) “Pattern Recognition and Machine Learning”, C. M. Bishop, Springer (2006) |
| Semester Requirements | Number of Activities | Level of Contribution |
| Attendance | % 0 | |
| Laboratory | % 0 | |
| Application | % 0 | |
| Field Work | % 0 | |
| Special Course Internship (Work Placement) | % 0 | |
| Quizzes | 5 | % 25 |
| Homework Assignments | % 0 | |
| Presentation | % 0 | |
| Project | 1 | % 15 |
| Seminar | % 0 | |
| Midterms | 1 | % 20 |
| Preliminary Jury | % 0 | |
| Final | 1 | % 40 |
| Paper Submission | % 0 | |
| Jury | % 0 | |
| Bütünleme | % 0 | |
| Total | % 100 | |
| PERCENTAGE OF SEMESTER WORK | % 45 | |
| PERCENTAGE OF FINAL WORK | % 55 | |
| Total | % 100 | |
| Activities | Number of Activities | Duration (Hours) | Workload |
| Course Hours | 13 | 3 | 39 |
| Laboratory | 0 | 0 | 0 |
| Application | 0 | 0 | 0 |
| Special Course Internship (Work Placement) | 0 | 0 | 0 |
| Field Work | 0 | 0 | 0 |
| Study Hours Out of Class | 13 | 8 | 104 |
| Presentations / Seminar | 0 | 0 | 0 |
| Project | 1 | 3 | 3 |
| Homework Assignments | 0 | 0 | 0 |
| Quizzes | 5 | 1 | 5 |
| Preliminary Jury | 0 | 0 | 0 |
| Midterms | 1 | 2 | 2 |
| Paper Submission | 0 | 0 | 0 |
| Jury | 0 | 0 | 0 |
| Final | 1 | 2 | 2 |
| Total Workload | 155 | ||
| No Effect | 1 Lowest | 2 Low | 3 Average | 4 High | 5 Highest |
| Program Outcomes | Level of Contribution |